thesantatitan/qwen-svg-sft-new-rank32
023
<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/> <details><summary>See axolotl config</summary>
axolotl version: 0.10.0.dev0
base_model: Qwen/Qwen3-8B
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: thesantatitan/text2svg-stack-follow-constraints-10k
type: chat_template
split: train
chat_template: tokenizer_default
field_messages: messages
roles_to_train: ["assistant"]
dataset_prepared_path: text2svg-prepared
val_set_size: 0.05
output_dir: ./lora-out
sequence_len: 4096
sample_packing: false
eval_sample_packing: false
pad_to_sequence_len: false
adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 32
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
lora_modules_to_save: # required when adding new tokens to LLaMA/Mistral
- embed_tokens
- lm_head
wandb_project: svg-sft-qwen-8b-saved
wandb_entity:
wandb_watch:
wandb_run_id: sexyrun1
gradient_accumulation_steps: 64
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.0001
bf16: auto
fp16: false
tf32: false
train_on_inputs: false
group_by_length: false
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 10
save_steps: 20
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
hub_strategy: every_save
hub_model_id: thesantatitan/qwen-svg-sft-new-rank32</details><br>
qwen-svg-sft-new-rank32
This model is a fine-tuned version of Qwen/Qwen3-8B on the thesantatitan/text2svg-stack-follow-constraints-10k dataset. It achieves the following results on the evaluation set:
- Loss: 0.7087
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- trainbatchsize: 1
- evalbatchsize: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradientaccumulationsteps: 64
- totaltrainbatch_size: 128
- totalevalbatch_size: 2
- optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
- lrschedulertype: cosine
- lrschedulerwarmup_steps: 10
- num_epochs: 1.0
Training results
Framework versions
- PEFT 0.15.2
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1
